{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:7667TSD3WOI65ETAT5POEB44GT","short_pith_number":"pith:7667TSD3","schema_version":"1.0","canonical_sha256":"ffbdf9c87bb391ee92609f5ee2079c34c799b0670abc6575d8d460db2c51e969","source":{"kind":"arxiv","id":"2406.05649","version":3},"attestation_state":"computed","paper":{"title":"GTR: Improving Large 3D Reconstruction Models through Geometry and Texture Refinement","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Aliaksandr Siarohin, Chaoyang Wang, Hsin-Ying Lee, Jiaxu Zou, Michael Vasilkovsky, Peiye Zhuang, Sergey Korolev, Sergey Tulyakov, Songfang Han, Vladislav Shakhrai","submitted_at":"2024-06-09T05:19:24Z","abstract_excerpt":"We propose a novel approach for 3D mesh reconstruction from multi-view images. Our method takes inspiration from large reconstruction models like LRM that use a transformer-based triplane generator and a Neural Radiance Field (NeRF) model trained on multi-view images. However, in our method, we introduce several important modifications that allow us to significantly enhance 3D reconstruction quality. First of all, we examine the original LRM architecture and find several shortcomings. Subsequently, we introduce respective modifications to the LRM architecture, which lead to improved multi-view"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2406.05649","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-09T05:19:24Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"88dd1c5e4342b1d1b94f6b52665bbea69913564780a098133204dc3ddd5a43b6","abstract_canon_sha256":"e6c3bf4ddf8c684a4d73a8aa9c34acce41b0d9d6226d5016cf6066c701e41bc7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:49:45.662646Z","signature_b64":"u5i19gXz8RmO15WywrV+ZMC+4n+L6/qEcmwuUcOJjnw21mNhd6VLkkzwMrttxSZlWE1ZmlP6VDzG9yk9pjR6AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ffbdf9c87bb391ee92609f5ee2079c34c799b0670abc6575d8d460db2c51e969","last_reissued_at":"2026-07-05T11:49:45.662182Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:49:45.662182Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GTR: Improving Large 3D Reconstruction Models through Geometry and Texture Refinement","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Aliaksandr Siarohin, Chaoyang Wang, Hsin-Ying Lee, Jiaxu Zou, Michael Vasilkovsky, Peiye Zhuang, Sergey Korolev, Sergey Tulyakov, Songfang Han, Vladislav Shakhrai","submitted_at":"2024-06-09T05:19:24Z","abstract_excerpt":"We propose a novel approach for 3D mesh reconstruction from multi-view images. Our method takes inspiration from large reconstruction models like LRM that use a transformer-based triplane generator and a Neural Radiance Field (NeRF) model trained on multi-view images. However, in our method, we introduce several important modifications that allow us to significantly enhance 3D reconstruction quality. First of all, we examine the original LRM architecture and find several shortcomings. Subsequently, we introduce respective modifications to the LRM architecture, which lead to improved multi-view"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.05649","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2406.05649/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2406.05649","created_at":"2026-07-05T11:49:45.662236+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.05649v3","created_at":"2026-07-05T11:49:45.662236+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.05649","created_at":"2026-07-05T11:49:45.662236+00:00"},{"alias_kind":"pith_short_12","alias_value":"7667TSD3WOI6","created_at":"2026-07-05T11:49:45.662236+00:00"},{"alias_kind":"pith_short_16","alias_value":"7667TSD3WOI65ETA","created_at":"2026-07-05T11:49:45.662236+00:00"},{"alias_kind":"pith_short_8","alias_value":"7667TSD3","created_at":"2026-07-05T11:49:45.662236+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.28125","citing_title":"CLEAR-NeRF: Collinearity and Local-region Enhanced Accurate 3D Reconstruction in Unbounded Scenes","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2605.31466","citing_title":"VolFill: Single-View Amodal 3D Scene Reconstruction with Volumetric Flow Matching","ref_index":100,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16990","citing_title":"DreamEdit3D: Personalization of Multi-View Diffusion Models for 3D Editing","ref_index":52,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7667TSD3WOI65ETAT5POEB44GT","json":"https://pith.science/pith/7667TSD3WOI65ETAT5POEB44GT.json","graph_json":"https://pith.science/api/pith-number/7667TSD3WOI65ETAT5POEB44GT/graph.json","events_json":"https://pith.science/api/pith-number/7667TSD3WOI65ETAT5POEB44GT/events.json","paper":"https://pith.science/paper/7667TSD3"},"agent_actions":{"view_html":"https://pith.science/pith/7667TSD3WOI65ETAT5POEB44GT","download_json":"https://pith.science/pith/7667TSD3WOI65ETAT5POEB44GT.json","view_paper":"https://pith.science/paper/7667TSD3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.05649&json=true","fetch_graph":"https://pith.science/api/pith-number/7667TSD3WOI65ETAT5POEB44GT/graph.json","fetch_events":"https://pith.science/api/pith-number/7667TSD3WOI65ETAT5POEB44GT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7667TSD3WOI65ETAT5POEB44GT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7667TSD3WOI65ETAT5POEB44GT/action/storage_attestation","attest_author":"https://pith.science/pith/7667TSD3WOI65ETAT5POEB44GT/action/author_attestation","sign_citation":"https://pith.science/pith/7667TSD3WOI65ETAT5POEB44GT/action/citation_signature","submit_replication":"https://pith.science/pith/7667TSD3WOI65ETAT5POEB44GT/action/replication_record"}},"created_at":"2026-07-05T11:49:45.662236+00:00","updated_at":"2026-07-05T11:49:45.662236+00:00"}